Search
K
OpenAI API

Creates a model response for the given chat conversation. Learn more in the [text generation](/docs/guides/text-generation), [vision](/docs/guides/vision), and [audio](/docs/guides/audio) guides. Parameter support can differ depending on the model used to generate the response, particularly for newer reasoning models. Parameters that are only supported for reasoning models are noted below. For the current state of unsupported parameters in reasoning models, [refer to the reasoning guide](/docs/guides/reasoning).

post
https://api.openai.com/v1/chat/completions

Body

application/json

CreateChatCompletionRequest

messagesOne Of
arrayrequired

A list of messages comprising the conversation so far. Depending on the
model you use, different message types (modalities) are
supported, like text,
images, and audio.

>= 1 items

Developer messageobject

Developer-provided instructions that the model should follow, regardless of
messages sent by the user. With o1 models and newer, developer messages
replace the previous system messages.

Show Child Parameters
modelAny Of
required

ID of the model to use. See the model endpoint compatibility table for details on which models work with the Chat API.

Example:gpt-4o

Variant 1string
storeboolean | null

Whether or not to store the output of this chat completion request for
use in our model distillation or
evals products.

Default:false

reasoning_effortstring | null

o1 and o3-mini models only

Constrains effort on reasoning for
reasoning models.
Currently supported values are low, medium, and high. Reducing
reasoning effort can result in faster responses and fewer tokens used
on reasoning in a response.

Allowed values:lowmediumhigh

Default:medium

metadataobject | null

Set of 16 key-value pairs that can be attached to an object. This can be
useful for storing additional information about the object in a structured
format, and querying for objects via API or the dashboard.

Keys are strings with a maximum length of 64 characters. Values are strings
with a maximum length of 512 characters.

frequency_penaltynumber | null

Number between -2.0 and 2.0. Positive values penalize new tokens based on
their existing frequency in the text so far, decreasing the model’s
likelihood to repeat the same line verbatim.

Default:0

>= -2<= 2

logit_biasobject | null

Modify the likelihood of specified tokens appearing in the completion.

Accepts a JSON object that maps tokens (specified by their token ID in the
tokenizer) to an associated bias value from -100 to 100. Mathematically,
the bias is added to the logits generated by the model prior to sampling.
The exact effect will vary per model, but values between -1 and 1 should
decrease or increase likelihood of selection; values like -100 or 100
should result in a ban or exclusive selection of the relevant token.

Default:null

logprobsboolean | null

Whether to return log probabilities of the output tokens or not. If true,
returns the log probabilities of each output token returned in the
content of message.

Default:false

top_logprobsinteger | null

An integer between 0 and 20 specifying the number of most likely tokens to
return at each token position, each with an associated log probability.
logprobs must be set to true if this parameter is used.

>= 0<= 20

max_tokensinteger | nullDEPRECATED

The maximum number of tokens that can be generated in the
chat completion. This value can be used to control
costs for text generated via API.

This value is now deprecated in favor of max_completion_tokens, and is
not compatible with o1 series models.

max_completion_tokensinteger | null

An upper bound for the number of tokens that can be generated for a completion, including visible output tokens and reasoning tokens.

ninteger | null

How many chat completion choices to generate for each input message. Note that you will be charged based on the number of generated tokens across all of the choices. Keep n as 1 to minimize costs.

Default:1

>= 1<= 128

Example:1

modalitiesarray | null[string]

Output types that you would like the model to generate for this request.
Most models are capable of generating text, which is the default:

["text"]

The gpt-4o-audio-preview model can also be used to generate audio. To
request that this model generate both text and audio responses, you can
use:

["text", "audio"]

Allowed values:textaudio

predictionOne Of

Configuration for a Predicted Output,
which can greatly improve response times when large parts of the model
response are known ahead of time. This is most common when you are
regenerating a file with only minor changes to most of the content.

Static Contentobject

Static predicted output content, such as the content of a text file that is
being regenerated.

Show Child Parameters
audioobject | null

Parameters for audio output. Required when audio output is requested with
modalities: ["audio"]. Learn more.

Show Child Parameters
presence_penaltynumber | null

Number between -2.0 and 2.0. Positive values penalize new tokens based on
whether they appear in the text so far, increasing the model’s likelihood
to talk about new topics.

Default:0

>= -2<= 2

response_formatOne Of

An object specifying the format that the model must output.

Setting to { "type": "json_schema", "json_schema": {...} } enables
Structured Outputs which ensures the model will match your supplied JSON
schema. Learn more in the Structured Outputs
guide.

Setting to { "type": "json_object" } enables JSON mode, which ensures
the message the model generates is valid JSON.

Important: when using JSON mode, you must also instruct the model
to produce JSON yourself via a system or user message. Without this, the
model may generate an unending stream of whitespace until the generation
reaches the token limit, resulting in a long-running and seemingly “stuck”
request. Also note that the message content may be partially cut off if
finish_reason="length", which indicates the generation exceeded
max_tokens or the conversation exceeded the max context length.

ResponseFormatTextobject
Show Child Parameters
seedinteger | null(int64)

This feature is in Beta.
If specified, our system will make a best effort to sample deterministically, such that repeated requests with the same seed and parameters should return the same result.
Determinism is not guaranteed, and you should refer to the system_fingerprint response parameter to monitor changes in the backend.

service_tierstring | null

Specifies the latency tier to use for processing the request. This parameter is relevant for customers subscribed to the scale tier service:

  • If set to ‘auto’, and the Project is Scale tier enabled, the system will utilize scale tier credits until they are exhausted.
  • If set to ‘auto’, and the Project is not Scale tier enabled, the request will be processed using the default service tier with a lower uptime SLA and no latency guarantee.
  • If set to ‘default’, the request will be processed using the default service tier with a lower uptime SLA and no latency guarantee.
  • When not set, the default behavior is ‘auto’.

Allowed values:autodefault

Default:auto

stopOne Of

Up to 4 sequences where the API will stop generating further tokens.

Default:null

Variant 1string | null
streamboolean | null

If set, partial message deltas will be sent, like in ChatGPT. Tokens will be sent as data-only server-sent events as they become available, with the stream terminated by a data: [DONE] message. Example Python code.

Default:false

stream_optionsobject | null

Options for streaming response. Only set this when you set stream: true.

Default:null

Show Child Parameters
temperaturenumber | null

What sampling temperature to use, between 0 and 2. Higher values like 0.8 will make the output more random, while lower values like 0.2 will make it more focused and deterministic.
We generally recommend altering this or top_p but not both.

Default:1

>= 0<= 2

Example:1

top_pnumber | null

An alternative to sampling with temperature, called nucleus sampling,
where the model considers the results of the tokens with top_p probability
mass. So 0.1 means only the tokens comprising the top 10% probability mass
are considered.

We generally recommend altering this or temperature but not both.

Default:1

>= 0<= 1

Example:1

toolsarray[object]

A list of tools the model may call. Currently, only functions are supported as a tool. Use this to provide a list of functions the model may generate JSON inputs for. A max of 128 functions are supported.

Show Child Parameters
tool_choiceOne Of

Controls which (if any) tool is called by the model.
none means the model will not call any tool and instead generates a message.
auto means the model can pick between generating a message or calling one or more tools.
required means the model must call one or more tools.
Specifying a particular tool via {"type": "function", "function": {"name": "my_function"}} forces the model to call that tool.

none is the default when no tools are present. auto is the default if tools are present.

Variant 1string

none means the model will not call any tool and instead generates a message. auto means the model can pick between generating a message or calling one or more tools. required means the model must call one or more tools.

Allowed values:noneautorequired

parallel_tool_callsboolean

Whether to enable parallel function calling during tool use.

Default:true

userstring

A unique identifier representing your end-user, which can help OpenAI to monitor and detect abuse. Learn more.

Example:user-1234

function_callOne Of
DEPRECATED

Deprecated in favor of tool_choice.

Controls which (if any) function is called by the model.

none means the model will not call a function and instead generates a
message.

auto means the model can pick between generating a message or calling a
function.

Specifying a particular function via {"name": "my_function"} forces the
model to call that function.

none is the default when no functions are present. auto is the default
if functions are present.

Variant 1string

none means the model will not call a function and instead generates a message. auto means the model can pick between generating a message or calling a function.

Allowed values:noneauto

functionsarray[object]DEPRECATED

Deprecated in favor of tools.

A list of functions the model may generate JSON inputs for.

>= 1 items<= 128 items

Show Child Parameters

Response

200

OK

CreateChatCompletionResponse

Represents a chat completion response returned by model, based on the provided input.

idstringrequired

A unique identifier for the chat completion.

choicesarray[object]required

A list of chat completion choices. Can be more than one if n is greater than 1.

Show Child Parameters
createdintegerrequired

The Unix timestamp (in seconds) of when the chat completion was created.

modelstringrequired

The model used for the chat completion.

service_tierstring | null

The service tier used for processing the request.

Allowed values:scaledefault

Example:scale

system_fingerprintstring

This fingerprint represents the backend configuration that the model runs with.

Can be used in conjunction with the seed request parameter to understand when backend changes have been made that might impact determinism.

objectstringrequired

The object type, which is always chat.completion.

Allowed values:chat.completion

usageobject

Usage statistics for the completion request.

Show Child Parameters
post/chat/completions

Body

{ "messages": [ { "content": {}, "role": "developer" } ], "model": {} }
 
200

Completions

Given a prompt, the model will return one or more predicted completions, and can also return the probabilities of alternative tokens at each position.

Creates a completion for the provided prompt and parameters.

post
https://api.openai.com/v1/completions

Body

application/json

CreateCompletionRequest

modelAny Of
required

ID of the model to use. You can use the List models API to see all of your available models, or see our Model overview for descriptions of them.

Variant 1string
promptOne Of
required

The prompt(s) to generate completions for, encoded as a string, array of strings, array of tokens, or array of token arrays.

Note that <|endoftext|> is the document separator that the model sees during training, so if a prompt is not specified the model will generate as if from the beginning of a new document.

Default:<|endoftext|>

Variant 1string

Default:

Example:This is a test.

best_ofinteger | null

Generates best_of completions server-side and returns the “best” (the one with the highest log probability per token). Results cannot be streamed.

When used with n, best_of controls the number of candidate completions and n specifies how many to return – best_of must be greater than n.

Note: Because this parameter generates many completions, it can quickly consume your token quota. Use carefully and ensure that you have reasonable settings for max_tokens and stop.

Default:1

>= 0<= 20

echoboolean | null

Echo back the prompt in addition to the completion

Default:false

frequency_penaltynumber | null

Number between -2.0 and 2.0. Positive values penalize new tokens based on their existing frequency in the text so far, decreasing the model’s likelihood to repeat the same line verbatim.

See more information about frequency and presence penalties.

Default:0

>= -2<= 2

logit_biasobject | null

Modify the likelihood of specified tokens appearing in the completion.

Accepts a JSON object that maps tokens (specified by their token ID in the GPT tokenizer) to an associated bias value from -100 to 100. You can use this tokenizer tool to convert text to token IDs. Mathematically, the bias is added to the logits generated by the model prior to sampling. The exact effect will vary per model, but values between -1 and 1 should decrease or increase likelihood of selection; values like -100 or 100 should result in a ban or exclusive selection of the relevant token.

As an example, you can pass {"50256": -100} to prevent the <|endoftext|> token from being generated.

Default:null

logprobsinteger | null

Include the log probabilities on the logprobs most likely output tokens, as well the chosen tokens. For example, if logprobs is 5, the API will return a list of the 5 most likely tokens. The API will always return the logprob of the sampled token, so there may be up to logprobs+1 elements in the response.

The maximum value for logprobs is 5.

Default:null

>= 0<= 5

max_tokensinteger | null

The maximum number of tokens that can be generated in the completion.

The token count of your prompt plus max_tokens cannot exceed the model’s context length. Example Python code for counting tokens.

Default:16

>= 0

Example:16

ninteger | null

How many completions to generate for each prompt.

Note: Because this parameter generates many completions, it can quickly consume your token quota. Use carefully and ensure that you have reasonable settings for max_tokens and stop.

Default:1

>= 1<= 128

Example:1

presence_penaltynumber | null

Number between -2.0 and 2.0. Positive values penalize new tokens based on whether they appear in the text so far, increasing the model’s likelihood to talk about new topics.

See more information about frequency and presence penalties.

Default:0

>= -2<= 2

seedinteger | null(int64)

If specified, our system will make a best effort to sample deterministically, such that repeated requests with the same seed and parameters should return the same result.

Determinism is not guaranteed, and you should refer to the system_fingerprint response parameter to monitor changes in the backend.

stopOne Of

Up to 4 sequences where the API will stop generating further tokens. The returned text will not contain the stop sequence.

Default:null

Variant 1string | null

Default:<|endoftext|>

Example:

streamboolean | null

Whether to stream back partial progress. If set, tokens will be sent as data-only server-sent events as they become available, with the stream terminated by a data: [DONE] message. Example Python code.

Default:false

stream_optionsobject | null

Options for streaming response. Only set this when you set stream: true.

Default:null

Show Child Parameters
suffixstring | null

The suffix that comes after a completion of inserted text.

This parameter is only supported for gpt-3.5-turbo-instruct.

Default:null

Example:test.

temperaturenumber | null

What sampling temperature to use, between 0 and 2. Higher values like 0.8 will make the output more random, while lower values like 0.2 will make it more focused and deterministic.

We generally recommend altering this or top_p but not both.

Default:1

>= 0<= 2

Example:1

top_pnumber | null

An alternative to sampling with temperature, called nucleus sampling, where the model considers the results of the tokens with top_p probability mass. So 0.1 means only the tokens comprising the top 10% probability mass are considered.

We generally recommend altering this or temperature but not both.

Default:1

>= 0<= 1

Example:1

userstring

A unique identifier representing your end-user, which can help OpenAI to monitor and detect abuse. Learn more.

Example:user-1234

Response

200 application/json

OK

CreateCompletionResponse

Represents a completion response from the API. Note: both the streamed and non-streamed response objects share the same shape (unlike the chat endpoint).

idstringrequired

A unique identifier for the completion.

choicesarray[object]required

The list of completion choices the model generated for the input prompt.

Show Child Parameters
createdintegerrequired

The Unix timestamp (in seconds) of when the completion was created.

modelstringrequired

The model used for completion.

system_fingerprintstring

This fingerprint represents the backend configuration that the model runs with.

Can be used in conjunction with the seed request parameter to understand when backend changes have been made that might impact determinism.

objectstringrequired

The object type, which is always “text_completion”

Allowed values:text_completion

usageobject

Usage statistics for the completion request.

Show Child Parameters
post/completions

Body

{ "model": {}, "prompt": "This is a test." }
 
200 application/json

Embeddings

Get a vector representation of a given input that can be easily consumed by machine learning models and algorithms.

Creates an embedding vector representing the input text.

post
https://api.openai.com/v1/embeddings

Body

application/json

CreateEmbeddingRequest

* Additional properties are NOT allowed.
inputOne Of
required

Input text to embed, encoded as a string or array of tokens. To embed multiple inputs in a single request, pass an array of strings or array of token arrays. The input must not exceed the max input tokens for the model (8192 tokens for text-embedding-ada-002), cannot be an empty string, and any array must be 2048 dimensions or less. Example Python code for counting tokens. Some models may also impose a limit on total number of tokens summed across inputs.

Example:The quick brown fox jumped over the lazy dog

stringstring

The string that will be turned into an embedding.

Default:

Example:This is a test.

modelAny Of
required

ID of the model to use. You can use the List models API to see all of your available models, or see our Model overview for descriptions of them.

Example:text-embedding-3-small

Variant 1string
encoding_formatstring

The format to return the embeddings in. Can be either float or base64.

Allowed values:floatbase64

Default:float

Example:float

dimensionsinteger

The number of dimensions the resulting output embeddings should have. Only supported in text-embedding-3 and later models.

>= 1

userstring

A unique identifier representing your end-user, which can help OpenAI to monitor and detect abuse. Learn more.

Example:user-1234

Response

200 application/json

OK

CreateEmbeddingResponse

dataarray[object]required

Represents an embedding vector returned by embedding endpoint.

Show Child Parameters
modelstringrequired

The name of the model used to generate the embedding.

objectstringrequired

The object type, which is always “list”.

Allowed values:list

usageobjectrequired

The usage information for the request.

Show Child Parameters
post/embeddings

Body

{ "input": "This is a test.", "model": {} }
 
200 application/json